LDIP: Long Distance Information Propagation for Video Super-Resolution
Michael Bernasconi, A. Djelouah, Y Zhang, M. Gross, C Schroers
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (Honolulu, US, October 19-23, 2025), pp. 11558-11567
Abstract
Video super-resolution (VSR) methods typically exploit information across multiple frames to achieve high quality upscaling, with recent approaches demonstrating impressive performance. Nevertheless, challenges remain, particularly in effectively leveraging information over long distances. To address this limitation in VSR, we propose a strategy for long distance information propagation with a flexible fusion module that can optionally also assimilate information from additional high resolution reference images. We design our overall approach such that it can leverage existing pre-trained VSR backbones and adapt the feature upscaling module to support arbitrary scaling factors. Our experiments demonstrate that we can achieve state-of-theart results on perceptual metrics and deliver more visually pleasing results compared to existing solutions.
